llama-stack

phoenix-oss/llama-stack

Fork 0

forked from phoenix-oss/llama-stack-mirror

Commit graph

2317a5bc18 Release candidate 0.1.6rc7 v0.1.6rc7 github-actions[bot] 2025-03-07 21:59:28 +00:00
3b4f3a6b15

test: update recorded fixtures (#1493) ehhuang 2025-03-07 13:58:38 -08:00
b0cc38b269

test: fix recordable mocks cache key (#1492) ehhuang 2025-03-07 13:45:25 -08:00
a1cdace093

test: image downloading is flaky (#1491) ehhuang 2025-03-07 13:39:26 -08:00
a8d0cdaf37

feat: updated inline vllm inference provider (#880) Fred Reiss 2025-03-07 13:38:23 -08:00
acbae66b9d

chore: escape tool output for logging (#1490) ehhuang 2025-03-07 13:33:45 -08:00
a55aab5958

fix: fix scoring tests (#1487) Xi Yan 2025-03-07 13:13:41 -08:00
e6355bfc3b

ci: enable Dependabot for GitHub Actions (#1470) Sébastien Han 2025-03-07 21:54:56 +01:00
5a2b9e121c

fix: return result for together's get_params (#1484) Xi Yan 2025-03-07 12:52:26 -08:00
1257288361

build: add 'tiktoken' to deps (#1483) ehhuang 2025-03-07 12:36:02 -08:00
124e8d7cfe

build: include .md (#1482) ehhuang 2025-03-07 12:10:52 -08:00
d86a893ead

fix: Swap to AsyncOpenAI client in remote vllm provider (#1459) Ben Browning 2025-03-07 14:48:00 -05:00
256448c14e

fix(cli): llama model prompt-format (#1481) ehhuang 2025-03-07 11:45:54 -08:00
ffa32af930

build: bump llama-stack-client version (#1469) Sébastien Han 2025-03-07 20:42:38 +01:00
7cf1e24c4e

feat(logging): implement category-based logging (#1362) Sébastien Han 2025-03-07 20:34:30 +01:00
bad12ee21f

fix: remove ruff N999 (#1388) Sébastien Han 2025-03-07 20:14:04 +01:00
fbd47bb4b6

feat(agent): plain function as client tool (#1479) ehhuang 2025-03-07 11:10:07 -08:00
1097912054

refactor: display defaults in help text (#1480) Charlie Doern 2025-03-07 14:05:58 -05:00
b8c519ba11

feat: rag eval lifecycle notebook (#1458) Xi Yan 2025-03-07 10:41:50 -08:00
511afe1381

chore: add pytest-report.xml to gitignore (#1473) Ihar Hrachyshka 2025-03-07 13:41:22 -05:00
40cd48fa09

chore: remove the incorrect output (#1472) Reid 2025-03-08 02:39:33 +08:00
c4b229f2c9

chore: Delete unused .gitmodules (#1460) Yuan Tang 2025-03-07 13:38:55 -05:00
649d9bc26d

fix(security): Bump jinja2 to >=3.1.6 (#1461) Yuan Tang 2025-03-07 13:38:39 -05:00
4dccf916d1

feat: open benchmark template and doc (#1465) Botao Chen 2025-03-07 10:37:55 -08:00
290cc843fc

test: first unit test for resolver (#1475) Ashwin Bharambe 2025-03-07 10:20:51 -08:00
60e7f3d705

fix: Revert "feat: record token usage for inference API (#1300)" (#1476) Dinesh Yeduguru 2025-03-07 10:16:47 -08:00
df4fbae35c

ci: Add script to generate changelog (#1463) Yuan Tang 2025-03-07 12:45:08 -05:00
4d9fe25bbf fix: fetched latest pypi version when building documentation Ashwin Bharambe 2025-03-06 21:15:15 -08:00
330cc9d09d

feat: add Milvus vectorDB (#1467) Ashwin Bharambe 2025-03-06 20:59:31 -08:00
1e3be1e4d7

fix: fix agent test recorded responses (#1462) Xi Yan 2025-03-06 19:37:52 -08:00
8234cdf1a5

fix(deps): move chardet and pypdf imports inline where used (#1434) Ihar Hrachyshka 2025-03-06 20:09:14 -05:00
803bf0e029

fix: solve ruff B008 warnings (#1444) Sébastien Han 2025-03-07 01:48:35 +01:00
3a454be9b2

docs: add back eval concept doc (#1456) Xi Yan 2025-03-06 15:47:20 -08:00
ca2910d27a

docs: update test_agents to use new Agent SDK API (#1402) ehhuang 2025-03-06 15:21:12 -08:00
3d71e5a036

test: recordable mocks use json only (#1443) ehhuang 2025-03-06 14:46:29 -08:00
564977c646

docs: update eval doc (#1453) Xi Yan 2025-03-06 14:14:10 -08:00
db4ee7a9ff

docs: improve rag doc (#1411) Reid 2025-03-07 06:03:52 +08:00
1a95271fab

fix: notebook vision inference (#1423) Xi Yan 2025-03-06 13:40:21 -08:00
46bc5f4a7a

chore: log exception (#1452) ehhuang 2025-03-06 11:42:51 -08:00
4bbb4ddeae

fix: resolve pydantic warning on .dict() usage (#1445) Sébastien Han 2025-03-06 20:27:47 +01:00
e8071b54dc fix: no skip_logger_removal for non-library client Ashwin Bharambe 2025-03-06 11:04:56 -08:00
14c9ebbae5

docs: Add CHANGELOG.md (#1440) Yuan Tang 2025-03-06 13:57:24 -05:00
8d86137ab2

docs: add information on how to set log level before running (#1430) Charlie Doern 2025-03-06 13:54:14 -05:00
bcb13c492f

test: revamp eval related integration tests (#1433) Xi Yan 2025-03-06 10:51:35 -08:00
82e94fe22f

ci: add Github workflow which runs unittests in PR (#1442) Ashwin Bharambe 2025-03-05 18:23:28 -08:00
e6ae557661 fix: update testing documentation Ashwin Bharambe 2025-03-05 17:41:13 -08:00
2fe976ed0a

refactor(test): introduce --stack-config and simplify options (#1404) Ashwin Bharambe 2025-03-05 17:02:02 -08:00
a0d6b165b0

chore: remove unused build dir (#1379) Reid 2025-03-06 07:40:00 +08:00
4d4be03176

fix: don't import from llama_models (#1436) Ihar Hrachyshka 2025-03-05 18:30:38 -05:00
6cf79437b3

feat: support ClientTool output metadata (#1426) ehhuang 2025-03-05 14:30:27 -08:00
ac717f38dc

chore: Reduce flakes in test_text_inference on smaller models (#1428) Ben Browning 2025-03-05 16:05:30 -05:00
b8535417e0

feat: record token usage for inference API (#1300) Dinesh Yeduguru 2025-03-05 12:41:45 -08:00
9c4074ed49

fix: Gracefully handle no choices in remote vLLM response (#1424) Ben Browning 2025-03-05 15:07:54 -05:00
bcc5370d2e

feat: effective agent workflow notebook (#1372) Xi Yan 2025-03-05 11:53:25 -08:00
1c6fbd95a5

fix: regex parser to support more answer formats (#1425) yyymeta 2025-03-05 11:52:07 -08:00
00570fde31

chore: Get sqlite_vec and vector_store unit tests passing (#1413) Ben Browning 2025-03-05 13:20:13 -05:00
77d323c2f8

docs: fix typo (#1416) Reid 2025-03-06 02:02:32 +08:00
d3508c4c76

feat(1/n): scoring function registration for llm-as-judge (#1405) Xi Yan 2025-03-05 10:00:34 -08:00
3d9331840e

docs: api documentation for agents/eval/scoring/datasets (#1400) Xi Yan 2025-03-05 09:40:24 -08:00
0d18274d34

chore: update hf source for eval notebook (#1403) Xi Yan 2025-03-05 09:38:30 -08:00
24a27baf7c

chore: Make README code blocks more easily copy pastable (#1420) Ellis Tarn 2025-03-05 09:11:01 -08:00
3fabe076cd

chore: Update CODEOWNERS (#1407) Botao Chen 2025-03-04 21:48:24 -08:00
fb998683e0

fix: Agent uses the first configured vector_db_id when documents are provided (#1276) Daniele Martinoli 2025-03-05 06:44:13 +01:00
78962be996

chore: refactor create_and_execute_turn and resume_turn (#1399) Xi Yan 2025-03-04 16:07:30 -08:00
abfbaf3c1b

refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) Ashwin Bharambe 2025-03-04 14:53:47 -08:00
dd0db8038b

refactor(test): unify vector_io tests and make them configurable (#1398) Ashwin Bharambe 2025-03-04 13:37:45 -08:00
fd8c991393

fix: rag as attachment bug (#1392) ehhuang 2025-03-04 13:08:16 -08:00
e9a37bad63

chore: rename task_config to benchmark_config (#1397) Xi Yan 2025-03-04 12:44:04 -08:00
158b6dc404

chore: deprecate allow_turn_resume (#1377) Xi Yan 2025-03-04 12:22:11 -08:00
cad5eed4b5

refactor(tests): delete inference, safety and agents tests from providers/tests/ (#1393) Ashwin Bharambe 2025-03-04 10:41:57 -08:00
4ca58eb987 refactor: tests/unittests -> tests/unit; tests/api -> tests/integration Ashwin Bharambe 2025-03-04 09:55:05 -08:00
c6b13b6a24 fix: pre-commit Ashwin Bharambe 2025-03-04 09:49:40 -08:00
1c63ec981a feat(test): allow specifying simple ad-hoc distributions in LLAMA_STACK_CONFIG Ashwin Bharambe 2025-03-04 09:42:00 -08:00
cb085d56c6

docs: fix typo (#1390) Reid 2025-03-05 01:02:55 +08:00
d57cffb495

fix(pgvector): replace hyphens with underscores in table names (#1385) Alexey Rybak 2025-03-04 07:06:35 -08:00
468edfd92c

fix: fix end of files for pre-commit (#1387) Sébastien Han 2025-03-04 16:05:02 +01:00
0b92fef3ba refine Botao Chen 2025-03-03 23:53:27 -08:00
840fd353f7 init commit Botao Chen 2025-03-03 23:41:11 -08:00
07a992ef90

feat: deterministic tools ordering (#1380) ehhuang 2025-03-03 20:38:07 -08:00
86fc514abb

refactor: move more tests, delete some providers tests (#1382) Ashwin Bharambe 2025-03-03 20:28:34 -08:00
e5ec68f66e fix: fix bugs in relative imports exposed due to dir move Ashwin Bharambe 2025-03-03 19:42:45 -08:00
55668d3c5b refactor: move a few tests to top-level tests/ directory Ashwin Bharambe 2025-03-03 17:33:39 -08:00
5736c7d682

refactor: move tests/client-sdk to tests/api (#1376) Ashwin Bharambe 2025-03-03 17:28:12 -08:00
c3155cb1bc fix: add a bunch more keys to be passed as provider data for client-sdk tests Ashwin Bharambe 2025-03-03 17:05:12 -08:00
5c9d12a206

chore: improve --port help text (#1346) Reid 2025-03-04 08:49:03 +08:00
0a76ece249 feat: add more logs to agent_instance.py Ashwin Bharambe 2025-03-03 16:15:47 -08:00
ee5e9b935a

feat: better using get_default_tool_prompt_format (#1360) ehhuang 2025-03-03 14:50:06 -08:00
386c806c70

test: introduce recordable mocks for Agent tests (#1268) ehhuang 2025-03-03 14:48:32 -08:00
816fdf289a refactor: move generation.py to llama3 Ashwin Bharambe 2025-03-03 13:38:06 -08:00
02066591b8 refactor: move generation.py to llama3 Ashwin Bharambe 2025-03-03 13:38:06 -08:00
725423c95c

refactor: move llama3 impl to meta_reference provider (#1364) Ashwin Bharambe 2025-03-03 13:22:57 -08:00
af396e3809 fix: update version and fix docs release notes link Ashwin Bharambe 2025-03-03 11:48:57 -08:00
789f918042 fix: add tomli to requirements.txt for docs; ideally we need to move this to uv Ashwin Bharambe 2025-03-03 11:11:17 -08:00
f86154dff5

refactor: restructure resolver logic and improve type safety (#1323) Sébastien Han 2025-03-03 19:45:12 +01:00
cae6c00d8a

fix: Fixed use of chunk.id (#1356) Daniele Martinoli 2025-03-03 19:42:59 +01:00
7d111c7510

feat: unify max_infer_iters in client/server agent loop (#1309) Xi Yan 2025-03-03 10:08:36 -08:00
754feba61f

feat: add a configurable category-based logger (#1352) Ashwin Bharambe 2025-03-02 18:51:14 -08:00
a9a7b11326

docs: update agent_execution_loop example code (#1350) Reid 2025-03-03 10:27:43 +08:00
58586f4f8c

fix: update cmd check logic (#1347) Reid 2025-03-03 10:26:59 +08:00
e84f1a5549

fix: fix pre-commit check issue (#1349) Reid 2025-03-03 00:13:17 +08:00